Performance Evaluation

In this section, we provide the performance statistics with different combinations of delegate and buffer conversion methods for : Object Detection which is introduced above.

Designed Pipeline for Object Detection

Note

The statistics are roughly recorded on experimental. To obtain exact statistics, you should run the APP on the platform. Performance may vary between different versions of the board image.

Genio 350-EVK

• Apply different conversion methods for the pipeline. This table only shows the statistics for applying NNAPI delegate, because it has the best performance of all based on the experimental results.

	USB Camera (resolution 1920*1080)		YUV camera (resolution 1920*1080)
Conversion Method	FPS	Inference Time(ms)	FPS	Inference Time(ms)
v4l2convert + v4l2convert	14	34	19	30
videoconvert + v4l2convert	14	34	4	33
v4l2convert + videoscale	5	34	5	31
videoconvert + videoscale	16	32	3	31

• Apply different delegates for the pipeline with the best conversion methods. For USB Camera, is videoconvert + videoscale, and for YUV camera, is v4l2convert + v4l2convert.

	USB Camera (resolution 1920*1080)		YUV camera (resolution 1920*1080)
Delegate	FPS	Inference Time(ms)	FPS	Inference Time(ms)
CPU	4	253	4	253
GPU	5	203	5	203
ArmNN(GpuAcc)	10	90	9	80
ArmNN(CpuAcc)	10	90	9	80
NNAPI(VP6)	16	32	19	30

Genio 1200-demo

API: Tensorflow Lite

• Apply different conversion methods for the pipeline. This table only shows the statistics for applying ARMNN(CpuAcc), because it has the best performance of all based on the experimental results.

	USB Camera (resolution 640*480)		YUV camera (resolution 2316*1746)
Convert Method	FPS	Inference Time(ms)	Unsupported yet
v4l2convert + v4l2convert	Unsupported yet
videoconvert + v4l2convert
v4l2convert + videoscale
videoconvert + videoscale	35	20

• Apply different delegates for the pipeline with the best conversion methods. For USB Camera, is videoconvert + videoscale.

	USB Camera (resolution 640*480)		YUV camera (resolution 2316*1746)
Delegate	FPS	Inference Time(ms)	Unsupported yet
CPU	8	125
GPU	30	31
ARMNN(GpuAcc)	31	25
ARMNN(CpuAcc)	35	20

API: Neuron

• Apply different conversion methods for the pipeline. The model used in this case was compiled with backend:mdla.

	USB Camera (resolution 640*480)		YUV camera (resolution 2316*1746)
Convert Method	FPS	Inference Time(ms)	Unsupported yet
v4l2convert + v4l2convert	Unsupported yet
videoconvert + v4l2convert
v4l2convert + videoscale
videoconvert + videoscale	5	30

Note

For how to convert tflite model to dla model, please refer to Neuron Compiler section.